Tepy.ai provides a silent-speech recognition platform that converts lip movements into audible speech or text. This enables hands-free, non-invasive communication for individuals with voice loss or in sound-sensitive environments, allowing them to control applications and interact with digital devices.
Funding
Funding not disclosed
Founders
Product
Problem
Individuals experiencing voice loss due to medical conditions or those requiring communication in sound-sensitive environments face significant barriers to interacting with digital devices and engaging in everyday conversations. Traditional voice recognition and input methods are inaccessible or impractical in these scenarios, leading to social isolation and reduced digital autonomy.
Solution
Tepy.ai offers a silent-speech recognition platform that translates lip movements into audible speech or text, enabling hands-free and non-invasive communication. The technology allows users to control applications, send messages, and interact with voice assistants using only their facial expressions. For individuals with voice loss, the platform can even reconstruct their original voice by utilizing uploaded audio recordings, providing a personalized and natural communication experience. This solution aims to restore communicative capabilities and facilitate seamless digital interfacing for a broader range of users.
Target Audience
The primary target audience includes individuals with voice loss (e.g., post-laryngectomy patients, non-verbal individuals) and professionals or users who need to communicate silently in environments where audible speech is disruptive.
Features
- Real-time lip movement analysis using advanced computer vision algorithms.
- Conversion of recognized lip movements into synthesized speech or text output.
- Optional voice reconstruction feature using user-provided audio samples for personalized vocal output.
- Hands-free operation, eliminating the need for physical input devices.
- Non-invasive user interface, requiring no surgical intervention.
- Integration capabilities for controlling applications and voice assistants.
- Support for diverse communication environments, including sound-sensitive or noisy settings.